Regression-based finite element machines for reliability modeling of downhole safety valves
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.ress.2020.106894 http://hdl.handle.net/11449/201574 |
Resumo: | Downhole Safety Valve (DHSV) stands for a device widely used in offshore wells to ensure the integrity and avoid uncontrolled leaks of oil and gas to the environment, known as blowouts. The reliability estimation of such valves can be used to predict the blowout occurrence and to evaluate the workover demand, as well as to assist decision-making actions. In this paper, we introduce FEMaR, a Finite Element Machine for regression problems, which figures no training step, besides being parameterless. Another main contribution of this work is to evaluate several machine learning models to estimate the reliability of DHSVs for further comparison against traditional statistical methods. The experimental evaluation over a dataset collected from a Brazilian oil and gas company showed that machine learning techniques are capable of obtaining promising results, even in the presence of censored information, and they can outperform the statistical approaches considered in this work. Such findings also investigated using uncertainty analysis, evidenced that we can save economic resources and increase the safety at the offshore well operations. |
id |
UNSP_dd3f28ee2cd309d6b71b2de0ff7cd7fc |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/201574 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Regression-based finite element machines for reliability modeling of downhole safety valvesFinite element machinesReliability predictionSafety valveDownhole Safety Valve (DHSV) stands for a device widely used in offshore wells to ensure the integrity and avoid uncontrolled leaks of oil and gas to the environment, known as blowouts. The reliability estimation of such valves can be used to predict the blowout occurrence and to evaluate the workover demand, as well as to assist decision-making actions. In this paper, we introduce FEMaR, a Finite Element Machine for regression problems, which figures no training step, besides being parameterless. Another main contribution of this work is to evaluate several machine learning models to estimate the reliability of DHSVs for further comparison against traditional statistical methods. The experimental evaluation over a dataset collected from a Brazilian oil and gas company showed that machine learning techniques are capable of obtaining promising results, even in the presence of censored information, and they can outperform the statistical approaches considered in this work. Such findings also investigated using uncertainty analysis, evidenced that we can save economic resources and increase the safety at the offshore well operations.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)CENPES/PETROBRAS, Rio de JaneiroDepartment of Production Engineering Fluminense Federal UniversityUniversity of Western São Paulo, Presidente PrudenteDepartment of Computing São Paulo State University - UNESPDepartment of Computing São Paulo State University - UNESPFAPESP: 2013/07375-0, 2014/12236-1FAPESP: 2016/19403-6CENPES/PETROBRASFluminense Federal UniversityUniversity of Western São PauloUniversidade Estadual Paulista (Unesp)Colombo, DaniloLima, Gilson Brito AlvesPereira, Danillo RobertoPapa, João P. [UNESP]2020-12-12T02:36:13Z2020-12-12T02:36:13Z2020-06-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.ress.2020.106894Reliability Engineering and System Safety, v. 198.0951-8320http://hdl.handle.net/11449/20157410.1016/j.ress.2020.1068942-s2.0-85079841089Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengReliability Engineering and System Safetyinfo:eu-repo/semantics/openAccess2021-10-22T20:28:46Zoai:repositorio.unesp.br:11449/201574Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-22T20:28:46Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Regression-based finite element machines for reliability modeling of downhole safety valves |
title |
Regression-based finite element machines for reliability modeling of downhole safety valves |
spellingShingle |
Regression-based finite element machines for reliability modeling of downhole safety valves Colombo, Danilo Finite element machines Reliability prediction Safety valve |
title_short |
Regression-based finite element machines for reliability modeling of downhole safety valves |
title_full |
Regression-based finite element machines for reliability modeling of downhole safety valves |
title_fullStr |
Regression-based finite element machines for reliability modeling of downhole safety valves |
title_full_unstemmed |
Regression-based finite element machines for reliability modeling of downhole safety valves |
title_sort |
Regression-based finite element machines for reliability modeling of downhole safety valves |
author |
Colombo, Danilo |
author_facet |
Colombo, Danilo Lima, Gilson Brito Alves Pereira, Danillo Roberto Papa, João P. [UNESP] |
author_role |
author |
author2 |
Lima, Gilson Brito Alves Pereira, Danillo Roberto Papa, João P. [UNESP] |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
CENPES/PETROBRAS Fluminense Federal University University of Western São Paulo Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Colombo, Danilo Lima, Gilson Brito Alves Pereira, Danillo Roberto Papa, João P. [UNESP] |
dc.subject.por.fl_str_mv |
Finite element machines Reliability prediction Safety valve |
topic |
Finite element machines Reliability prediction Safety valve |
description |
Downhole Safety Valve (DHSV) stands for a device widely used in offshore wells to ensure the integrity and avoid uncontrolled leaks of oil and gas to the environment, known as blowouts. The reliability estimation of such valves can be used to predict the blowout occurrence and to evaluate the workover demand, as well as to assist decision-making actions. In this paper, we introduce FEMaR, a Finite Element Machine for regression problems, which figures no training step, besides being parameterless. Another main contribution of this work is to evaluate several machine learning models to estimate the reliability of DHSVs for further comparison against traditional statistical methods. The experimental evaluation over a dataset collected from a Brazilian oil and gas company showed that machine learning techniques are capable of obtaining promising results, even in the presence of censored information, and they can outperform the statistical approaches considered in this work. Such findings also investigated using uncertainty analysis, evidenced that we can save economic resources and increase the safety at the offshore well operations. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-12T02:36:13Z 2020-12-12T02:36:13Z 2020-06-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1016/j.ress.2020.106894 Reliability Engineering and System Safety, v. 198. 0951-8320 http://hdl.handle.net/11449/201574 10.1016/j.ress.2020.106894 2-s2.0-85079841089 |
url |
http://dx.doi.org/10.1016/j.ress.2020.106894 http://hdl.handle.net/11449/201574 |
identifier_str_mv |
Reliability Engineering and System Safety, v. 198. 0951-8320 10.1016/j.ress.2020.106894 2-s2.0-85079841089 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Reliability Engineering and System Safety |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1792962390448406528 |